Universität Wien
Warning! The directory is not yet complete and will be amended until the beginning of the term.

250110 VO Introduction to Reinforcement Learning (2022S)

3.00 ECTS (2.00 SWS), SPL 25 - Mathematik
Moodle

Registration/Deregistration

Note: The time of your registration within the registration period has no effect on the allocation of places (no first come, first served).
Register/Deregister for this course

Details

Language: English

Examination dates

Lecturers

Classes (iCal) - next class is marked with N

  • Friday 04.03. 09:45 - 11:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Friday 18.03. 09:45 - 11:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Friday 25.03. 09:45 - 11:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Friday 01.04. 09:45 - 11:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Friday 08.04. 09:45 - 11:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Friday 29.04. 09:45 - 11:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Friday 06.05. 09:45 - 11:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Friday 13.05. 09:45 - 11:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Friday 20.05. 09:45 - 11:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Friday 27.05. 09:45 - 11:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Friday 03.06. 09:45 - 11:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Friday 10.06. 09:45 - 11:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Friday 17.06. 09:45 - 11:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
  • Friday 24.06. 09:45 - 11:15 Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock

Information

Aims, contents and method of the course

This course will cover the mathematics of reinforcement learning specially in the context of deep neural networks.

The goal of the course: We start form basics of probability and stochastics, describe the problem of reinforcement learning. This is an optimization problem, and we discuss both theoretical solutions and some optimization algorithms used in practice.

Topics covered in the course will include:
1 Review of probability and stochastics.
2. Markov Decision Process and the modeling of a reinforcement learning problem
3. Exact solutions and adding stochasticity.
4. Policy gradient estimation
5. Practical policy optimization methods such as TRPO and PPO.

Assessment and permitted materials

To get a grade on the course you must either do the final exam or submit a course project/paper.

Minimum requirements and assessment criteria

• Basic Probability and Statistics
• Basics of optimization (constraint optimization, cost functions, gradient descent, etc.)
• Familiarity with machine learning will be useful but not necessary.

Examination topics

Reading list

There is no official textbook for the class. Some references with links are listed on moodle.

Association in the course directory

MAMV

Last modified: We 03.07.2024 00:17